Skip to content

armgit / burr

Public Imported from GitHub
0

Build applications that make decisions (chatbots, agents, simulations, etc...). Monitor, trace, persist, and execute on your own infrastructure.

Adds quick gif to README to demonstrate what burr does

elijahbenizzy27193ad41f01
diff --git a/README.md b/README.md
index 55641cff..be2e5b01 100644
--- a/README.md
+++ b/README.md
@@ -6,6 +6,7 @@ Burr is a state machine for data/AI projects. You can (and should!) use it for a
is always hard!
You can find the documentation [here](https://studious-spork-n8kznlw.pages.github.io/).
+
## What can you do with Burr?
Burr can be used for a variety of applications. Burr can build a state machine to orchestrate, express, and track:
@@ -20,8 +21,10 @@ Using hooks and other integrations you can (a) integrate with any of your favori
(b) build custom actions that delegate to your favorite libraries.
Bur will *not* tell you how to build your models, how to query APIs, or how to manage your data. It will help you tie all these together
-in a way that scales with your needs and makes following the logic of your system easy.
+in a way that scales with your needs and makes following the logic of your system easy. Burr comes out of the box with a host of integrations
+including tooling to build a UI in streamlit and watch your state machine execute.
+![Burr at work](./chatbot.gif)
## Why the name Burr?
@@ -30,6 +33,7 @@ We imagine a world in which Burr and Hamilton lived in harmony and saw through t
built Burr as a _harness_ to handle state between executions of Hamilton DAGs,
but realized that it has a wide array of applications and decided to release it.
+
# Getting Started
To get started, install from `pypi`, using your favorite package manager:
diff --git a/chatbot.gif b/chatbot.gif
new file mode 100644
index 00000000..e9ecdfaf
Binary files /dev/null and b/chatbot.gif differ
diff --git a/examples/gpt/streamlit_app.py b/examples/gpt/streamlit_app.py
index f9e4ee7b..13cb8eff 100644
--- a/examples/gpt/streamlit_app.py
+++ b/examples/gpt/streamlit_app.py
@@ -79,7 +79,7 @@ def main():
"...", disabled=st.session_state.get("running", False), key="chat_input"
)
should_rerun = chatbot_step(app_state, prompt)
- with st.container(height=800):
+ with st.container(height=850):
for item in app_state.history:
render_chat_message(item)
with columns[1]: